Information processing system and information processing method

Abstract

To immediately notify a user of the timing for obtaining an optimal degree of fermentation of feed.SOLUTION: An information processing system (100) comprises: an odor measurement device (30) equipped with multiple odor sensor elements; and an estimation unit (13) which inputs feature values based on measurement signals output by the odor measurement device (30) and the elapsed time since the start of ongoing storage into a pre-trained model, and outputs an estimation result from estimating a degree of fermentation of the feed currently in storage.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to an information processing system and an information processing method. [Background technology]

[0002] In recent years, devices have been developed that estimate the state of a specific object based on the odor of the object. For example, Patent Document 1 describes an odor identification device that uses coke odor and tar odor, which are odors collected from assumed odor sources in a steel plant, as reference odors and identifies the source and cause of unknown odors in a steel plant or the like. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2006-017467 Summary of the Invention [Problem to be solved by the invention]

[0004] Harvested grass and other feed (silage) is stored in a silo (feed storage facility) under specified conditions to promote lactic acid fermentation and other processes before being fed to livestock. In order to check the fermentation status of grass and other feed, the silo must be opened, the stored feed must be sampled, and the pH, moisture content, lactic acid content, butyric acid content, and acetic acid content must be measured, which requires a lot of time and effort. In addition, opening the silo carries a high risk of introducing bacteria from the air outside the silo, so it is a task that should be avoided as much as possible.

[0005] One aspect of the present invention is to provide an information processing system, an information processing method, and the like that can instantly inform a user of the timing when the fermentation state of feed has become satisfactory. [Means for solving the problem]

[0006] An information processing system according to one embodiment of the present invention comprises an acquisition unit that acquires a measurement signal from an odor measuring device that measures the odor of feed stored in a silo and outputs a measurement signal, and an estimation unit that inputs the feature values ​​based on the measurement signal output from the odor measuring device that measures the odor of the feed being stored and the elapsed time since the start of current storage into a trained model obtained by machine learning using teacher data including explanatory variables including a combination of information on storage conditions when feed was stored in the silo in the past, the elapsed time since the start of storage, and feature values ​​based on the measurement signal, and a target variable including fermentation degree information indicating the degree of fermentation of the feed at the elapsed time, and outputs an estimation result that estimates the degree of fermentation of the feed currently being stored, wherein the odor measuring device comprises a plurality of odor sensor elements, and the measurement signal is output from each of the plurality of odor sensor elements.

[0007] An information processing method according to one embodiment of the present invention includes an acquisition step in which a computer acquires a measurement signal from an odor measuring device that measures the odor of feed stored in a silo, and an estimation step in which the computer inputs the feature values ​​based on the measurement signal output from the odor measuring device that measures the odor of the feed being stored and the elapsed time since the start of current storage into a learned model obtained by machine learning using teacher data including explanatory variables including a combination of information on storage conditions when feed was stored in the silo in the past, the elapsed time since the start of storage, and feature values ​​based on the measurement signal, and a target variable including fermentation degree information indicating the degree of fermentation of the feed at the elapsed time, and outputs an estimation result that estimates the degree of fermentation of the feed currently being stored, wherein the odor measuring device has a plurality of odor sensor elements, and the measurement signal is output from each of the plurality of odor sensor elements. Effect of the Invention

[0008] According to one aspect of the present invention, it is possible to provide an information processing system and an information processing method capable of accurately estimating the degree of fermentation of feed. [Brief description of the drawings]

[0009] [Figure 1] 1 is a schematic diagram illustrating an example of a configuration of an information processing system according to an embodiment of the present invention. [Diagram 2] 1 is a functional block diagram showing an example of an odor measuring device according to an embodiment of the present invention. [Diagram 3] FIG. 2 is a top view showing an example of the configuration of an odor sensor element. [Figure 4] 1 is a functional block diagram showing an example of a configuration of an estimation device according to an embodiment of the present invention. [Diagram 5] 5 is a flowchart showing an example of a process flow in which an information processing system according to one embodiment of the present invention estimates a fermentation state of stored feed. [Figure 6] 1 is a functional block diagram showing an example of a configuration of an estimation device according to an embodiment of the present invention. [Figure 7] 1 is a schematic diagram illustrating an example of a configuration of an information processing system according to an embodiment of the present invention. [Figure 8] 1 is a schematic diagram illustrating an example of a configuration of an information processing system according to an embodiment of the present invention. [Figure 9] 1 is a functional block diagram showing an example of a configuration of an information processing system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] An embodiment of the present invention will be described below, but the present invention is not limited thereto. In addition, unless otherwise specified in this specification, "A to B" representing a numerical range means "A or more and B or less."

[0011] [Embodiment 1] (Information processing system 100) First, an overview of an information processing system 100 according to an embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a schematic diagram showing an example of the configuration of an information processing system 100 according to an embodiment of the present invention.

[0012] As shown in FIG. 1, the information processing system 100 includes an odor measuring device 30, an estimation device 10, and a user terminal 50. The odor measuring device 30 can output a measurement signal based on an odor substance contained in the feed stored in the silo. The user terminal 50 is a terminal device such as a personal computer used by a user who uses the information processing system 100, and transmits a detection signal to the estimation device 10 and receives the estimation result. The estimation device 10 can output an estimation result that estimates the fermentation state of the currently stored feed based on a feature based on the measurement signal and the elapsed time from the start of the current storage. The estimation device 10 may perform estimation based on information on the storage conditions of the currently stored feed in addition to the feature and the elapsed time. Note that the present time means the timing when the odor measuring device 30 measures the odor of the stored feed that is the estimation target of the estimation device 10. As shown in FIG. 1, the information processing system 100 may include a user terminal 50 and an estimation device 10 connected via a wide area communication network 40. Furthermore, the user terminal 50 and the odor measuring device 30 may be connected by a local area network connection, LTE communication, or the like, without going through a provider or the like.

[0013] The wide area communication network 40 is not particularly limited, and may be the Internet, a telephone line network, a mobile communication network, a CATV communication network, a satellite communication network, etc. The wide area communication network 40 may further be connected to a cloud server that stores the detection signal output by the odor measuring device 30 and the estimation result output by the estimation device 10. When the wide area communication network 40 is connected to a cloud server, the estimation device 10 may be realized as the cloud server.

[0014] According to the above configuration, the information processing system 100 inputs information on the storage conditions of the currently stored feed, the time elapsed since the start of storage, and features based on a measurement signal measuring the odor of the stored feed into the trained model to estimate the fermentation level of the currently stored feed. Here, the trained model is machine-learned using training data including explanatory variables including combinations of the storage conditions, the time elapsed since the start of storage, and features based on the measurement signal when the feed was previously stored, and a response variable including fermentation degree information indicating the fermentation level of the feed over the elapsed time.

[0015] This enables the information processing system 100 to instantly notify the user of the timing when the fermentation state of the feed becomes satisfactory.

[0016] The number of odor measuring devices 30 included in the information processing system 100 according to one embodiment of the present invention is not particularly limited, and may be one or more, three or more, five or more, or ten or more. Furthermore, the odor measuring devices 30 may be installed in silos provided in different locations, or some or all of them may be installed in silos provided in the same location.

[0017] In the information processing system 100, the connection between the estimation device 10 and the odor measurement device 30 may be a wired connection or a wireless connection. The estimation device 10 and the odor measurement device 30 may be connected via a wide area communication network. The estimation device 10 may be configured on a server capable of communicating with the odor measurement device 30. In this case, the information processing system 100 may include a device such as a terminal device that outputs the estimation result by the estimation device 10 and allows the user to understand the estimation result.

[0018] In the information processing system 100, the odor measuring device 30 includes a plurality of sensor elements. The measurement signal is output from each of the plurality of odor sensor elements. The sensor elements will be described below. After that, the odor measuring device 30 to which the odor sensor element 31 is applied, and the information processing system 100 including the odor measuring device 30 and the estimation device 10 will be described in detail.

[0019] The multiple sensor elements included in the odor measuring device 30 may be capable of measuring different odor substances, or may be capable of measuring the same odor substance.

[0020] (Odor measuring device 30) The outline and effects of an odor measurement device 30 to which an odor sensor element 31 is applied will be described below with reference to Fig. 2. Fig. 2 is a functional block diagram showing an example of the configuration of an information processing system 100 including an odor measurement device 30 to which an odor sensor element 31 is applied. The odor measurement device 30 includes an odor sensor element 31 that detects odor substances, a power source 32 (power supply), a clock 33 (timer), a control unit 34, and a communication unit 35. As described above, the odor measurement device 30 may be connected to a user terminal 50.

[0021] The odor measuring device 30 is disposed, for example, at a position where the gas in the silo can reach. A filter may be provided on the path of the gas in the silo until it reaches the position where the odor measuring device 30 is disposed. The filter may be, for example, an activated carbon filter. The position where the odor measuring device 30 is disposed may be, for example, a wall surface within the silo where the gas in the silo can reach. If necessary, a fan or the like may be installed that can supply air containing an odorant toward the odor sensor element 31 of the odor measuring device 30.

[0022] The "position where the gas in the silo can reach" may be any position where the gas in the silo can reach, and may be inside or outside the silo. For example, the odor measuring device 30 may be disposed at a position where the gas in the silo can be guided to the odor measuring device 30 by a fan or a vent, or at a position where the gas can reach the odor measuring device 30 by natural movement.

[0023] The power supply 32 is a power supply for supplying power to the odor sensor element 31. The constant voltage power supply 32 supplies a constant current (for example, a direct current of 1 mA) via a lead wire to the odor sensor element 31. The voltage value supplied by the constant voltage power supply 32 is 0.5V to 10V, for example, 2.5V or 5.0V.

[0024] The clock 33 measures the time. The clock 33 transmits the measured time to the control unit 34. The clock 33 may be a clock in which the time is set by the user, or may be a radio-controlled clock.

[0025] The control unit 34 controls each part of the odor measuring device. The control unit 34 also outputs the odor detected by the odor sensor element 31 as a measurement signal. The control unit 34 may output the odor measurement signal according to the time measured by the clock 33. The control unit 34 may also output information indicating the time when the odor was detected together with the measurement signal.

[0026] The communication unit 35 transmits the measurement signal output by the control unit 34. The communication unit 35 transmits the measurement signal to the wide area communication network 40, and the transmitted measurement signal is acquired by the estimation device 10.

[0027] The odor measuring device 30 may further include a housing, although this is not a required component. The housing is a container capable of containing air containing an odor substance. When the odor measuring device 30 includes a housing, the odor sensor element 31 is disposed within the housing.

[0028] The odor measuring device 30 outputs a measurement signal that indicates the change over time in the electrical conductivity of the odor sensor element 31 before and after an odor substance is adsorbed to the odor sensor element 31. This makes it possible to detect and identify various odor substances.

[0029] <Odor sensor element 31> 2 is a top view showing an example of the configuration of an odor sensor element 31. The odor sensor element 31 includes an odorant receiving layer 315 containing the above-mentioned resin composition, a first metal wiring 313A, and a second metal wiring 313B. In the following description, when there is no need to distinguish between the first metal wiring 313A and the second metal wiring 313B, they may be referred to as metal wiring 313.

[0030] The first metal wiring 313A and the second metal wiring 313B are metal wirings that function as electrodes for measuring changes in the electrical conductivity of the odorant receiving layer 315 (i.e., the resin composition). That is, the first metal wiring 313A and the second metal wiring 313B are spaced apart from each other, and the odorant receiving layer 315 is in contact with at least a portion of the first metal wiring and at least a portion of the second metal wiring. In one example, the first metal wiring 313A and the second metal wiring 313B are metal wirings that are not in direct contact with each other, and may be metal wirings that are approximately parallel to each other, as shown in FIG. 2.

[0031] 2, metal wiring 313 including first metal wiring 313A and second metal wiring 313B may be disposed on substrate 311. Substrate 311 may be a substrate such as glass epoxy that is generally used in electronic circuits. Metal wiring 313 may be a metal wiring such as copper or gold. The thickness of each of first metal wiring 313A and second metal wiring 313B as viewed in a direction perpendicular to the surface of the substrate may be, for example, 10 μm to 2 mm.

[0032] The odorant receiving layer 315 may be in contact with at least a portion of the first metal wiring 313A and at least a portion of the second metal wiring 313B. The odorant receiving layer 315 may be arranged to fill the area between the first metal wiring 313A and the second metal wiring 313B, as shown in FIG.

[0033] When the electrical conductivity of the odorant receiving layer 315 (ie, the electrical conductivity of the odor sensor element 31) is low, it is desirable that the distance between the first metal wiring 313A and the second metal wiring 313B be a predetermined distance (eg, 500 μm) or less.

[0034] The odorant receiving layer may contain a resin composition. The resin composition may contain a resin and may further contain one or more types selected from a surfactant and a filler (e.g., a conductive carbon material). In this specification, the term "odorant receiving layer" refers to a layer that adsorbs an odorant to be identified. The odorant receiving layer 315 is formed from the above-mentioned resin composition. The odorant receiving layer 315 may be provided as a part of the odor sensor element 31. The odorant receiving layer 315 changes its electrical resistance value depending on the adsorption of an odorant, etc. In other words, the odor sensor element 31 is an odor detection device that includes such an odorant receiving layer 315, and the odor measurement method of the odor sensor element 31 may be a chemiresistor type. In addition, the odor sensor element 31 is not limited to the above-mentioned chemiresistor type odor sensor element, and may include one or more types of odor sensor elements used in known odor sensors, etc.

[0035] When the odor sensor element 31 is a chemiresistor type containing a resin composition, the change in electrical conductivity over time differs between when odor substance A is adsorbed and when odor substance B, which is different from odor substance A, is adsorbed, so that it is possible to detect and distinguish various odor substances. In the odor measurement device 30 described later, a plurality of odor sensor elements 31 are arranged, each of which includes a substrate 311 on which a configuration for detecting an odor substance (metal wiring 313 and an odor substance receiving layer 315) is provided. A plurality of sets including an odor substance receiving layer 315 are arranged on each substrate 311. Each of the plurality of odor sensor elements 31 may be equipped with a constant voltage power supply and a voltmeter. In the odor measurement device 30, one configuration for detecting an odor substance (metal wiring 313 and an odor substance receiving layer 315) may be arranged on each substrate 311. Alternatively, in the odor measurement device 30, a plurality of sets of a configuration for detecting an odor substance (metal wiring 313 and an odor substance receiving layer 315) may be arranged on one substrate 311. In the latter case, a constant voltage power supply and a voltmeter are connected to each of the sets provided on the substrate 311.

[0036] The resin compositions contained in the odorant receiving layers 315 of the multiple odor sensor elements 31 included in the odor measurement device 30 may be the same or different. In other words, the multiple odor sensor elements 31 included in the odor measurement device 30 may have the same measurable odorant or may be different from each other. In addition, some of the multiple odor sensor elements 31 included in the odor measurement device 30 may have the same measurable odorant, and the remaining odor sensor elements 31 may have different measurable odorants. When the odorant receiving layers 315 included in the multiple odor sensor elements 31 have the same composition, each of the multiple odorant receiving layers 315 can detect the same odorant. When the multiple odor sensor elements 31 each include an odorant receiving layer 315 with a different composition, each of the multiple odorant receiving layers 315 responds differently to the odorant. In this way, by providing multiple sets of configurations for detecting odorants, the odor measurement device 30 can improve the accuracy of odorant identification.

[0037] The odor measuring device 30 described above can output the change over time in the electrical conductivity of the odor sensor element 31 for each odor substance when various odor substances are adsorbed to the odor sensor element 31. By applying this odor measuring device 30, it is possible to compare the change over time in the electrical conductivity of the odor sensor element 31 when odor substance A is adsorbed to the odor sensor element 31 with the change over time in the electrical conductivity of the odor sensor element 31 when odor substance B is adsorbed to the odor sensor element 31. Based on such a comparison result, it is possible to realize an estimation device 10 that can estimate the fermentation state of currently stored feed, which will be described later, from the odor substances adsorbed to the odor sensor element 31.

[0038] (Estimation device 10) The following describes the outline and effects of the estimation device 10. The estimation device 10 is a device that estimates the fermentation state of the currently stored feed from the measurement signal output from the above-mentioned odor measurement device 30. The estimation device 10 uses a trained model obtained by machine learning, so it can determine odor substances with high accuracy. The estimation device 10 may perform estimation based on a sensor signal obtained from a device other than the odor measurement device 30. The device other than the odor measurement device 30 is a device such as a sensor that can detect information related to the fermentation state of the feed, and may be, for example, a carbon dioxide sensor, a temperature sensor, or a humidity sensor. The estimation device 10 may use a signal obtained from the odor measurement device 30 and a signal from a device other than the above-mentioned odor measurement device 30.

[0039] 1 is a functional block diagram showing an example of the configuration of the estimation device 10. The estimation device 10 includes a control unit 1 that controls each unit of the estimation device 10, and a storage unit 2 that stores various data used by the estimation device 10, but is not limited to this configuration. For example, the storage unit 2 may be an external device attached to the estimation device 10. Furthermore, the estimation device 10 may be connected to the wide area communication network 40 as described above.

[0040] <Control unit 1> First, the control unit 1 will be described. The control unit 1 includes a measurement signal acquisition unit 11, an extraction unit 12, an estimation unit 13, and a communication unit 14. In addition, some of the blocks included in the control unit 1 may be omitted from the control unit 1 by giving the functions of the blocks to another device capable of communicating with the estimation device 10. For example, the function of the communication unit 14 may be given to a device capable of acquiring the estimation result from the estimation device 10. In this case, the estimation device 10 may transmit the result estimated by the estimation unit 13 via the other device.

[0041] The measurement signal acquiring unit 11 acquires a measurement signal output from the odor measuring device 30. Specifically, the measurement signal acquiring unit 11 acquires a detection signal from each of the multiple odor sensor elements 31. The measurement signal acquiring unit 11 may acquire the measurement signal in real time, or may acquire the measurement signal at a predetermined time interval (e.g., 0.1 second interval). The measurement signal acquiring unit 11 preferably acquires the measurement signal every first hour. The measurement signal acquiring unit 11 may store the acquired measurement signal data in the storage unit 2.

[0042] The first time period may be, for example, but is not limited to, 1 minute, 5 minutes, 10 minutes, 30 minutes, 1 hour, 2 hours, 4 hours, 6 hours, 8 hours, 10 hours, or more.

[0043] The extraction unit 12 extracts a feature quantity indicating a feature of a target odor from the measurement signal acquired by the measurement signal acquisition unit 11. The feature quantity extracted by the extraction unit 12 may be, for example, a value related to at least one of the signal intensity and the change over time of the measurement signal output from each of the multiple odor sensor elements included in the odor measurement device 30.

[0044] More specifically, the feature amount may be a signal intensity ratio of the measurement signals output by a plurality of odor sensor elements, or a difference in the signal intensity of the measurement signal output by a specific odor sensor element with respect to the signal intensity of the measurement signal output by another odor sensor element. Furthermore, the feature amount may be a waveform showing a change over time of the measurement signal, or a pattern of the change over time of the measurement signal.

[0045] The feature amount may be a difference or ratio between the signal strength of a measurement signal measuring the odor of the stored feed to the signal strength of a measurement signal output by the odor measuring device 30 based on a reference gas such as compressed air or dry nitrogen. Alternatively, the feature amount may be a difference or ratio between the signal strength of a measurement signal measuring the odor of the stored feed to a preset threshold. Alternatively, the feature amount may be a difference or ratio between the signal strength of a measurement signal measuring the odor of the stored feed to the signal strength of a measurement signal at a time point prior to the time to be estimated.

[0046] The estimation unit 13 inputs data indicating the feature amount based on the measurement signal and the elapsed time from the start of the storage of the feed to the present to the trained model 21, and estimates the fermentation state of the currently stored feed. The measurement signal may be measurement signal data stored in the memory unit 2. The estimation unit 13 may estimate the fermentation state of the feed, for example, by class classification. The estimation device 10 may store information indicating the time (date and time) when the storage of the feed was started. In this case, the estimation unit 13 may specify the elapsed time from the start of the storage of the feed to the present based on the information and the current time. Alternatively, the estimation unit 13 may acquire information indicating the elapsed time from the odor measurement device 30. The estimation unit 13 may also acquire a count value obtained by counting a clock or the like from a reference time (for example, the start of the operation of the estimation device 10 or the start of the storage of the feed) as the elapsed time.

[0047] The estimation unit 13 may estimate the degree of fermentation of the feed, for example, the stage of fermentation, such as the feed not being fermented at all, the feed being about half fermented, or the feed being completely fermented, as the fermentation state of the feed. The estimation unit 13 may also estimate a value indicating the degree of fermentation of the feed, for example, a numerical value indicating the current fermentation state of the feed when the feed is completely fermented is set to 1. The estimation unit 13 may further estimate how the fermentation of the feed is progressing, based on the estimation results at multiple timings and the elapsed time. The estimation unit 13 may store the estimation result data in the memory unit 2.

[0048] The communication unit 14 transmits the estimation result estimated by the estimation unit 13 to the user terminal 50 via the wide area communication network 40 based on the user terminal data 22. The communication unit 14 may transmit the estimation result directly to the user terminal 50, or may transmit the estimation result to a web page or the like on the wide area communication network 40 that is accessible by the user terminal 50.

[0049] The estimation device 10 may further include a judgment unit that judges whether a fermentation state is good or bad based on the estimation result by the estimation unit 13. The judgment unit acquires the estimation result indicating the fermentation state of the feed by the estimation unit 13, and judges whether the fermentation state of the feed is good or bad based on a preset threshold value. For example, if the value indicating the fermentation state of the feed estimated by the estimation unit 13 is within a threshold value range, the judgment unit judges that the fermentation state of the feed is good, and if the value is outside the threshold value range, the judgment unit judges that the fermentation state of the feed is bad. When the estimation device 10 includes a judgment unit, the communication unit 14 may transmit the judgment result by the judgment unit in addition to the estimation result by the estimation unit 13.

[0050] <Storage section 2> Next, the storage unit 2 will be described. The storage unit 2 may store a trained model 21 and user terminal data 22. Furthermore, measurement signal data and estimation result data may be further stored as necessary. Furthermore, the storage unit 2 may store data indicating the time when storage of the feed began.

[0051] The measurement signal data is data of a measurement signal output from the odor measuring device 30 and acquired by the measurement signal acquiring unit 11. The measurement signal data may be labeled with information such as the measurement time, the measurement location, the identification number of the odor measuring device 30, and the type of measurement signal pattern.

[0052] The trained model 21 is trained by machine learning using training data. The training data includes the following explanatory variables and objective variables. The explanatory variables include information about the storage conditions when feed was stored in the silo in the past, the time elapsed since storage began, and a combination of features based on the measurement signal output from an odor measuring device 30 that measured the odor of the feed during storage. The objective variable includes fermentation degree information indicating the degree of fermentation of the feed over the time elapsed since the start of storage of the feed.

[0053] The trained model 21 may be generated using a known machine learning algorithm. Examples of machine learning algorithms that can be used to generate the trained model 21 include the k-nearest neighbor method, logistic regression, support vector machine, random forest, and neural network.

[0054] The estimation result data is a result of estimating the fermentation state of the currently stored feed, output from the estimation unit 13. The estimation result data may be labeled with the same information as the measurement signal data on which the estimation is based.

[0055] The user terminal data 22 is data related to a terminal owned by a user of the information processing system 100. The user terminal data 22 is data for linking the user terminal 50 with a measurement signal transmitted from the user terminal 50. An example of a user of the information processing system 100 is a manager who manages silage on-site.

[0056] (Processing performed by information processing system 100) An overview of an information processing method according to an embodiment of the present invention will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an overview of an information processing method by the information processing system 100.

[0057] In step S1, the odor measuring device 30 measures the odor of the feed stored in the silo and outputs a measurement signal. At this time, the odor measuring device 30 may output the odor measurement result to the estimation device 10 in real time, or may output it every first hour as described above.

[0058] In step S2, the measurement signal acquiring unit 11 acquires the measurement signal output from the odor measuring device 30 (acquisition step). The measurement signal acquiring unit 11 may acquire the measurement signal in real time, or may acquire the measurement signal at a predetermined time interval (e.g., 0.1 second interval). The measurement signal acquiring unit 11 may store the acquired measurement signal in the storage unit 2.

[0059] In step S3, the extraction unit 12 extracts a feature from the measurement signal. The extraction unit 12 may extract, as the feature, for example, a ratio or difference of the measurement signals, a waveform indicating a change over time in the measurement signal, or a pattern of the change over time in the measurement signal.

[0060] In step S4, the estimation unit 13 inputs the feature amount extracted in step S3 into the trained model 21 to estimate the fermentation state of the currently stored feed (estimation step). At this time, the trained model 21 is obtained by machine learning using the training data. The explanatory variables and the objective variables included in the training data are as described above. The estimation unit 13 may store the output estimation result in the memory unit 2.

[0061] In step S5, the communication unit 14 transmits (outputs) the estimation result estimated by the estimation unit 13 based on the user terminal data 22 to the user terminal 50 via the wide area communication network 40.

[0062] Harvested grass and other feed (silage) is stored in a silo (feed storage facility) under specified conditions to promote lactic acid fermentation and other processes before being fed to livestock. In order to check the fermentation status of grass and other feed, the silo must be opened, the stored feed must be sampled, and the pH, moisture content, lactic acid content, butyric acid content, and acetic acid content must be measured, which requires a lot of time and effort. In addition, opening the silo carries a high risk of introducing bacteria from the air outside the silo, so it is a task that should be avoided as much as possible.

[0063] When the information processing system 100 is used, the estimation unit 13 inputs information on the storage conditions during current storage, the time elapsed since the start of storage, and features based on a measurement signal measuring the smell of the feed during storage into the trained model to estimate the fermentation level of the feed currently being stored. Here, the trained model is machine-learned using training data including explanatory variables including combinations of the storage conditions, the time elapsed since the start of storage, and features based on the measurement signal when the feed was previously stored, and a response variable including fermentation degree information indicating the fermentation level of the feed over the elapsed time.

[0064] This allows the information processing system 100 to accurately estimate the fermentation state of the feed and instantly inform the user of the timing when the fermentation state of the feed becomes good. Furthermore, in the information processing system 100, if the estimation device 10 performs estimation at predetermined time intervals and outputs the estimation result, the user can grasp the fermentation state of the feed in real time. The user can take appropriate measures by grasping the fermentation state of the feed and the timing when the fermentation state of the feed becomes good. For example, when the fermentation state of the feed becomes good, an operation to stop the fermentation of the feed can be performed. Furthermore, the user can manage the fermentation of the feed more appropriately by grasping the relationship between the elapsed time, the fermentation state of the feed, and the storage conditions of the feed.

[0065] [Embodiment 2] An outline of an estimation device 10a according to another embodiment of the present invention will be described below with reference to Fig. 6. Note that the description of matters that have already been described will be omitted.

[0066] (Configuration of Estimation Device 10a) FIG. 6 is a functional block diagram showing an example of the configuration of an estimation device 10a different from that of the first embodiment.

[0067] The estimation device 10a includes a control unit 1 that controls each unit of the estimation device 10a, a memory unit 2a that stores various data used by the information processing device, and an input unit 15 that inputs information regarding the storage conditions of the feed.

[0068] The input unit 15 is for accepting various input operations from a user, and may be, for example, a keyboard, a mouse, a touch panel, or the like.

[0069] <Storage section 2a> The memory unit 2a may store a trained model 21a.

[0070] In addition to the items described above as explanatory variables, the trained model 21a further includes information on the feed storage conditions, such as the type of feed, the storage amount, the environment of the silo in which the feed is stored, etc. By including this information as explanatory variables in the trained model 21a, it becomes possible to more accurately estimate the fermentation state of the currently stored feed based on the information input from the input unit 15.

[0071] [Embodiment 3] Hereinafter, an overview of an information processing system 100a according to another embodiment of the present invention will be described with reference to Fig. 7. Fig. 7 is a schematic diagram showing an example of the configuration of an information processing system 100a different from those of embodiments 1 and 2. Note that descriptions of matters that have already been described will be omitted.

[0072] 7, in the information processing system 100a, a measurement signal output by an odor measuring device 30 is transmitted to an estimation device 10 via a wide area communication network 40. In addition, a user terminal 50 receives, via the wide area communication network 40, an estimation result output from the estimation device 10 based on the measurement signal.

[0073] The information processing system 100a includes an estimation device 10, an odor measurement device 30, and a user terminal 50. The information processing system 100a may include a wide area communication network 40 as necessary. As described above, in the information processing system 100a, the odor measurement device 30, the estimation device 10, and the user terminal 50 may be connected via the wide area communication network 40.

[0074] In the information processing system 100a, the user terminal data 22 may further include data in which the device number of the odor measuring device 30 and the terminal number of the user terminal 50 are linked together, in addition to the data described above.

[0075] With the above configuration, it is possible to transmit the estimation result to a user in an area distant from the odor measuring device 30, for example, a user terminal 50 used by a manager who remotely manages silage. Furthermore, when there are multiple silages being managed and the information processing system 100a includes multiple odor measuring devices 30 provided for each of the multiple silages, it is possible to transmit the estimation result based on the measurement signal measured at multiple locations. Furthermore, when the information processing system 100a is used by users at multiple locations, the information processing system 100a includes multiple user terminals 50, and can transmit the estimation result based on the measurement signal to each of the user terminals 50 at the multiple locations.

[0076] [Embodiment 4] Hereinafter, an overview of an information processing system 100b according to another embodiment of the present invention will be described with reference to Fig. 8. Fig. 8 is a schematic diagram showing an example of the configuration of the information processing system 100b. Note that descriptions of matters that have already been described will be omitted.

[0077] As shown in Fig. 8, in the information processing system 100b, the measurement signal output by the odor measuring device is directly transmitted to the estimation device 10a. The estimation device 10a outputs the result of estimating the fermentation state of the currently stored feed based on the acquired measurement signal. In other words, it can be said that in the information processing system 100b, the estimation device 10a is integrated with the user terminal 50. In addition, in the information processing system 100b, the estimation device 10a and the odor measuring device 30 may be connected by a local area network connection, LTE communication, or the like, without going through a provider or the like.

[0078] (Configuration of information processing system 100b) 9 is a functional block diagram showing an example of the configuration of an information processing system 100b different from those of embodiments 1 to 3. The information processing system 100b includes an estimation device 10b and an odor measuring device 30. The information processing system 100b may include a wide area communication network 40 as necessary.

[0079] The estimation device 10b includes a control unit 1a that controls each unit of the estimation device 10b, a storage unit 2 that stores various data used by the estimation device 10b, and an output unit 17 that outputs the estimation result.

[0080] <Control unit 1a> The control unit 1 a includes a measurement signal acquisition unit 11 , an extraction unit 12 , an estimation unit 13 , and an output control unit 16 .

[0081] The output control unit 16 causes the output unit 17 to output the estimation result output by the estimation unit 13. The output mode of the output unit 17 is not particularly limited, and may be, for example, a display output, a print output, or an audio output.

[0082] With the above configuration, since the estimation device 10a is integrated with the user terminal 50, the time lag until an estimation result is obtained is reduced.

[0083] [Software implementation example] In the information processing devices 100 and 100a, the control block (particularly the control unit 1) may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or may be realized by software.

[0084] In the latter case, the information processing device 100, 100a includes a computer that executes instructions of a program, which is software that realizes each function. The computer includes, for example, one or more processors, and a computer-readable recording medium that stores the program. The object of the present invention is achieved by the processor reading the program from the recording medium and executing it in the computer. The processor may be, for example, a CPU (Central Processing Unit). The recording medium may be a "non-transient tangible medium", such as a ROM (Read Only Memory), as well as a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like. The computer may further include a RAM (Random Access Memory) that expands the program. The program may be supplied to the computer via any transmission medium (such as a communication network or a broadcast wave) that can transmit the program. Note that one aspect of the present invention may also be realized in the form of a data signal embedded in a carrier wave, in which the program is embodied by electronic transmission.

[0085] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

[0086] 〔summary〕 The information processing system according to a first aspect of the present invention comprises an acquisition unit that acquires a measurement signal from an odor measuring device that measures the odor of feed stored in a silo and outputs a measurement signal, and an estimation unit that inputs the feature values ​​based on the measurement signal output from the odor measuring device that measures the odor of the feed being stored and the elapsed time since the start of current storage into a trained model obtained by machine learning using teacher data including explanatory variables including a combination of information on storage conditions when feed was stored in the silo in the past, the elapsed time since the start of storage, and feature values ​​based on the measurement signal, and a target variable including fermentation degree information indicating the degree of fermentation of the feed at the elapsed time, and outputs an estimation result that estimates the degree of fermentation of the feed currently being stored, wherein the odor measuring device comprises a plurality of odor sensor elements, and the measurement signal is output from each of the plurality of odor sensor elements.

[0087] In the information processing system according to aspect 2 of the present invention, in the above aspect 1, the feature may be a value related to at least one of the signal intensity and the change over time of the measurement signal output from each of the multiple odor sensor elements.

[0088] An information processing system according to a third aspect of the present invention is in the above-mentioned first or second aspect, wherein the odor measuring device is disposed at a position reachable by gas in the silo.

[0089] The information processing method according to aspect 4 of the present invention includes an acquisition step in which a computer acquires a measurement signal from an odor measuring device that measures the odor of feed stored in a silo, and an estimation step in which the computer inputs the feature values ​​based on the measurement signal output from the odor measuring device that measures the odor of the feed being stored and the elapsed time since the start of current storage into a trained model obtained by machine learning using teacher data including explanatory variables including a combination of information on storage conditions when feed was stored in the silo in the past, the elapsed time since the start of storage, and feature values ​​based on the measurement signal, and a target variable including fermentation degree information indicating the degree of fermentation of the feed at the elapsed time, and outputs an estimation result that estimates the degree of fermentation of the feed currently being stored, wherein the odor measuring device has a plurality of odor sensor elements, and the measurement signal is output from each of the plurality of odor sensor elements.

[0090] A fifth aspect of the present invention may be a control program for causing a computer to function as the information processing system of any one of the first to third aspects, and may be a control program for causing a computer to function as the acquisition unit, the estimation unit, and the determination unit.

[0091] A sixth aspect of the present invention may be a computer-readable recording medium having the control program according to the fifth aspect recorded thereon. [Explanation of symbols]

[0092] 10, 10a, 10b Estimation device 30 Odor measuring device 40 Wide Area Communication Network 50 User terminal 31 Odor sensor element 100, 100a, 100b Information Processing Systems 311 Substrate 313A 1st metal wiring 313B 2nd metal wiring 315 Odor receptor layer W Lead Wire

Claims

1. An acquisition unit that acquires a measurement signal from an odor measuring device that measures the odor of the feed stored in the silo and outputs a measurement signal; an estimation unit that inputs the feature quantities based on the measurement signals output from the odor measuring device that measures the odor of the feed being stored and the elapsed time from the start of current storage into a trained model obtained by machine learning using training data including explanatory variables including a combination of information on storage conditions when feed was previously stored in the silo, the elapsed time from the start of storage, and feature quantities based on the measurement signals, and a target variable including fermentation degree information indicating the degree of fermentation of the feed at the elapsed time, and outputs an estimation result that estimates the degree of fermentation of the feed being currently stored; Equipped with The odor measuring device includes a plurality of odor sensor elements, The measurement signal is output from each of the plurality of odor sensor elements. Information processing system.

2. The feature amount is a value related to at least one of the signal intensity and the change over time of the measurement signal output from each of the plurality of odor sensor elements; The information processing system according to claim 1 .

3. The odor measuring device is disposed at a position within the silo where the gas can reach. The information processing system according to claim 1 .

4. An acquisition step in which a computer acquires a measurement signal from an odor measuring device that measures the odor of the feed stored in the silo; an estimation step in which the computer inputs the feature quantities based on the measurement signal output from the odor measuring device measuring the odor of the feed being stored and the elapsed time from the start of current storage into a trained model obtained by machine learning using teacher data including explanatory variables including a combination of information on storage conditions when feed was previously stored in the silo, the elapsed time from the start of storage, and feature quantities based on the measurement signal, and a target variable including fermentation degree information indicating the degree of fermentation of the feed at the elapsed time, and outputs an estimation result that estimates the degree of fermentation of the feed being currently stored; Including, The odor measuring device includes a plurality of odor sensor elements, The measurement signal is output from each of the plurality of odor sensor elements. Information processing methods.

5. A control program for causing a computer to function as the information processing system according to claim 1 , the control program causing a computer to function as the acquisition unit and the estimation unit.

6. A computer-readable recording medium having the control program according to claim 5 recorded thereon.

Images